Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    descriptions of products related to durability and functionality, particularly in performance contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſind
    -1.02
     iſt
    -0.98
     itſelf
    -0.90
     ་་
    -0.87
     ―――――
    -0.81
     –,
    -0.80
    ˮ
    -0.79
    ſelf
    -0.79
     AppColors
    -0.78
    .",
    -0.77
    POSITIVE LOGITS
     stuff
    0.91
     my
    0.79
     I
    0.76
     mierda
    0.75
     crappy
    0.75
     kinda
    0.74
     دیگه
    0.73
     you
    0.73
     maybe
    0.72
     stupid
    0.70
    Act Density 2.180%

    No Known Activations